How to Use the Azure Cognitive Search MCP in Google ADK

Q: Can a Google ADK agent pull a specific document by its key from Azure Cognitive Search?

Yes, it uses the getdocument tool. Your agent passes the unique key, and the tool fetches the corresponding document from Azure. It's a direct and efficient way to retrieve a specific piece of information.

Q: Is it possible for my Google ADK agent to list all available indexes in Azure Cognitive Search?

Absolutely. The listindexes tool is designed for this. Your Google ADK agent can call it to get a complete list of indexes in your Azure Cognitive Search instance, which is useful for discovery or diagnostics.

Q: My agent is on Google Cloud. Can it see the text enrichment skillsets in Azure Cognitive Search?

It can. The listskillsets tool gives your agent visibility into the enrichment pipelines running in Azure. This helps it understand how the data is structured and what kind of information it can expect to find.

Give your Google ADK agent direct access to Azure Cognitive Search, right from your Google Cloud environment.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Azure Cognitive Search MCP to Google ADK

Create your Vinkius account to connect Azure Cognitive Search to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Azure Cognitive Search with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute Multi-Cloud Search

Your agent, running on Google Cloud, can now query data stored in Azure. Use the `search_documents` tool for standard text search or `vector_search` for more nuanced, meaning-based retrieval from your Azure Cognitive Search indexes. This is a game-changer for multi-cloud setups. Your Gemini-powered agent can take results from an Azure search, combine them with data from a BigQuery table, and reason over the entire dataset using its large context window. No more data silos.

Monitor Azure Infrastructure from GCP

This MCP Server gives your ADK agent visibility into your Azure search setup. It can call `list_indexes` to see what's available or use `list_indexers` to check if data is flowing correctly. It’s like having a cross-platform monitoring tool, but for your agent. Imagine an agent that builds a daily report by pulling metrics from both Google Cloud Monitoring and your Azure search service. You don't have to write custom API clients or manage credentials across clouds; the agent just uses the tools it's given.

Build Smarter Query Strategies

An agent can do more than just run a blind search. With the `get_index` and `list_skillsets` tools, your ADK agent can inspect an index's schema and enrichment pipeline before it even constructs a query. Armed with this information, a Gemini model can make smarter decisions. It can decide if a keyword search is better than a vector search for a given task, or it can tailor its query to match the specific fields and enrichments available in the Azure index.

Setup guide

Set up Azure Cognitive Search MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Azure Cognitive Search tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Azure Cognitive Search_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Azure Cognitive Search tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Azure Cognitive Search. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Azure Cognitive Search now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Azure Cognitive Search MCP in Google ADK

Simply add this MCP toolset to your agent's configuration. It exposes tools like `search_documents` and `vector_search`, allowing your Google ADK agent to query your Azure Cognitive Search indexes directly from its Google Cloud environment.

Yes, it uses the `get_document` tool. Your agent passes the unique key, and the tool fetches the corresponding document from Azure. It's a direct and efficient way to retrieve a specific piece of information.

Absolutely. The `list_indexes` tool is designed for this. Your Google ADK agent can call it to get a complete list of indexes in your Azure Cognitive Search instance, which is useful for discovery or diagnostics.

It can. The `list_skillsets` tool gives your agent visibility into the enrichment pipelines running in Azure. This helps it understand how the data is structured and what kind of information it can expect to find.

The connection is tightly controlled. Vinkius isolates each request, and the server only accesses the Azure Cognitive Search index configurations and document data that your agent explicitly queries. Nothing is persisted.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript